Mengdi Wang
Identifiers
- name variant Mengdi Wang 0.60 · backfill
Papers (49)
- Qumus: Realization of An Embodied AI Quantum Material Experimentalist cond-mat.mes-hall · 2026 · author #16
- WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer cs.GR · 2026 · author #5
- MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory cs.CV · 2026 · author #14
- Learning Agent Routing From Early Experience cs.CL · 2026 · author #9
- Matrix-Free Multigrid with Algebraically Consistent Coarsening on Adaptive Octrees math.NA · 2026 · author #1
- Autogenesis: A Self-Evolving Agent Protocol cs.AI · 2026 · author #8
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning cs.LG · 2026 · author #299
- Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity cs.LG · 2026 · author #4
- FlashSampling: Fast and Memory-Efficient Exact Sampling cs.LG · 2026 · author #6
- OpenClaw-RL: Train Any Agent Simply by Talking cs.CL · 2026 · author #4
- Interactive Benchmarks cs.AI · 2026 · author #9
- Deep Delta Learning cs.LG · 2026 · author #3
- Evaluating Large Language Models in Scientific Discovery cs.AI · 2025 · author #46
- CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency cs.CL · 2025 · author #19
- Higher-order Linear Attention cs.LG · 2025 · author #3
- ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization cs.LG · 2025 · author #3
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cs.AI · 2025 · author #27
- ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning cs.AI · 2025 · author #7
- Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary cs.AI · 2025 · author #6
- MMaDA: Multimodal Large Diffusion Language Models cs.CV · 2025 · author #7
- PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Docking cs.LG · 2025 · author #8
- Relative Translation Invariant Wasserstein Distance cs.LG · 2024 · author #4
- Feature-Based Q-Learning for Two-Player Stochastic Games cs.LG · 2019 · author #3
- RL4health: Crowdsourcing Reinforcement Learning for Knee Replacement Pathway Optimization cs.LG · 2019 · author #2
- Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound cs.LG · 2019 · author #2
- Learning to Control in Metric Space with Optimal Regret cs.LG · 2019 · author #3
- Sample-Optimal Parametric Q-Learning Using Linearly Additive Features cs.LG · 2019 · author #2
- Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks cs.CV · 2018 · author #1
- Towards Coherent and Cohesive Long-form Text Generation cs.CL · 2018 · author #7
- Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains math.OC · 2018 · author #2
- Diffusion Approximations for Online Principal Component Estimation and Global Convergence stat.ML · 2018 · author #2
- Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model math.OC · 2018 · author #2
- Scalable Bilinear $\pi$ Learning Using State and Action Features cs.LG · 2018 · author #3
- Estimation of Markov Chain via Rank-Constrained Likelihood stat.ML · 2018 · author #2
- Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization cs.LG · 2018 · author #3
- Approximation Methods for Bilevel Programming math.OC · 2018 · author #2
- Multi-Level Stochastic Gradient Methods for Nested Composition Optimization math.OC · 2018 · author #2
- Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality cs.LG · 2017 · author #2
- Primal-Dual $\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems cs.LG · 2017 · author #1
- Online Factorization and Partition of Complex Networks From Random Walks cs.LG · 2017 · author #4
- Lower Bound On the Computational Complexity of Discounted Markov Decision Problems cs.CC · 2017 · author #2
- Randomized Linear Programming Solves the Discounted Markov Decision Problem In Nearly-Linear (Sometimes Sublinear) Running Time math.OC · 2017 · author #1
- Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning stat.ML · 2016 · author #2
- Finite-sum Composition Optimization via Variance Reduced Gradient Descent math.OC · 2016 · author #2
- Accelerating Stochastic Composition Optimization math.OC · 2016 · author #1
- Near-Optimal Stochastic Approximation for Online Principal Component Estimation math.OC · 2016 · author #2
- Random Multi-Constraint Projection: Stochastic Gradient Methods for Convex Optimization with Many Constraints stat.ML · 2015 · author #1
- Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions math.OC · 2015 · author #3
- Stochastic Compositional Gradient Descent: Algorithms for Minimizing Compositions of Expected-Value Functions stat.ML · 2014 · author #1
Mentions
- 2409.02416 #4 · arxiv_oai · confidence 0.70 Mengdi Wang
- 2604.15034 #8 · arxiv_oai · confidence 0.70 Mengdi Wang
- 2605.18407 #16 · arxiv_oai · confidence 0.70 Mengdi Wang
- 2605.15305 #5 · arxiv_oai · confidence 0.70 Mengdi Wang
- 2512.00417 #19 · arxiv_oai · confidence 0.70 Mengdi Wang
- 2603.04737 #9 · arxiv_oai · confidence 0.70 Mengdi Wang
Frequent Coauthors
- Lin F. Yang 7 shared papers
- Yichen Chen 5 shared papers
- Yifan Zhang 5 shared papers
- Tuo Zhao 4 shared papers
- Ethan X. Fang 3 shared papers
- Han Liu 3 shared papers
- Hongru Wang 3 shared papers
- Jiahao Qiu 3 shared papers
- Ming Yin 3 shared papers
- Quanquan Gu 3 shared papers
- Shilong Liu 3 shared papers
- Xinzhe Juan 3 shared papers
- Cheng Qian 2 shared papers
- Chris Junchi Li 2 shared papers
- Heng Ji 2 shared papers
- Ji Liu 2 shared papers
- Kaixuan Huang 2 shared papers
- Ling Yang 2 shared papers
- Lin Yang 2 shared papers
- Minghao Guo 2 shared papers